{"id":"https://openalex.org/W2612420304","doi":"https://doi.org/10.1109/iscslp.2016.7918435","title":"Multi-channel feature adaptation for robust speech recognition","display_name":"Multi-channel feature adaptation for robust speech recognition","publication_year":2016,"publication_date":"2016-10-01","ids":{"openalex":"https://openalex.org/W2612420304","doi":"https://doi.org/10.1109/iscslp.2016.7918435","mag":"2612420304"},"language":"en","primary_location":{"id":"doi:10.1109/iscslp.2016.7918435","is_oa":false,"landing_page_url":"https://doi.org/10.1109/iscslp.2016.7918435","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2016 10th International Symposium on Chinese Spoken Language Processing (ISCSLP)","raw_type":"proceedings-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":false,"oa_status":"closed","oa_url":null,"any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5083198820","display_name":"Zhaofeng Zhang","orcid":"https://orcid.org/0000-0003-1797-7507"},"institutions":[{"id":"https://openalex.org/I119806805","display_name":"Nagaoka University","ror":"https://ror.org/02rcadd38","country_code":"JP","type":"education","lineage":["https://openalex.org/I119806805"]},{"id":"https://openalex.org/I85922643","display_name":"Nagaoka University of Technology","ror":"https://ror.org/00ys1hz88","country_code":"JP","type":"education","lineage":["https://openalex.org/I85922643"]}],"countries":["JP"],"is_corresponding":true,"raw_author_name":"Zhaofeng Zhang","raw_affiliation_strings":["Nagaoka University of Technology, Japan"],"affiliations":[{"raw_affiliation_string":"Nagaoka University of Technology, Japan","institution_ids":["https://openalex.org/I119806805","https://openalex.org/I85922643"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101602536","display_name":"Xiong Xiao","orcid":"https://orcid.org/0009-0001-5128-6518"},"institutions":[{"id":"https://openalex.org/I172675005","display_name":"Nanyang Technological University","ror":"https://ror.org/02e7b5302","country_code":"SG","type":"education","lineage":["https://openalex.org/I172675005"]}],"countries":["SG"],"is_corresponding":false,"raw_author_name":"Xiong Xiao","raw_affiliation_strings":["Temasek Laboratories, Nanyang Technological University (NTU), Singapore"],"affiliations":[{"raw_affiliation_string":"Temasek Laboratories, Nanyang Technological University (NTU), Singapore","institution_ids":["https://openalex.org/I172675005"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101745213","display_name":"Longbiao Wang","orcid":"https://orcid.org/0000-0002-8094-6861"},"institutions":[{"id":"https://openalex.org/I162868743","display_name":"Tianjin University","ror":"https://ror.org/012tb2g32","country_code":"CN","type":"education","lineage":["https://openalex.org/I162868743"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Longbiao Wang","raw_affiliation_strings":["Tianjin University, China"],"affiliations":[{"raw_affiliation_string":"Tianjin University, China","institution_ids":["https://openalex.org/I162868743"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5017251198","display_name":"Jianwu Dang","orcid":"https://orcid.org/0000-0002-9237-4821"},"institutions":[{"id":"https://openalex.org/I162868743","display_name":"Tianjin University","ror":"https://ror.org/012tb2g32","country_code":"CN","type":"education","lineage":["https://openalex.org/I162868743"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Jianwu Dang","raw_affiliation_strings":["Tianjin University, China"],"affiliations":[{"raw_affiliation_string":"Tianjin University, China","institution_ids":["https://openalex.org/I162868743"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5036393534","display_name":"Masahiro Iwahashi","orcid":"https://orcid.org/0000-0002-7566-1247"},"institutions":[{"id":"https://openalex.org/I119806805","display_name":"Nagaoka University","ror":"https://ror.org/02rcadd38","country_code":"JP","type":"education","lineage":["https://openalex.org/I119806805"]},{"id":"https://openalex.org/I85922643","display_name":"Nagaoka University of Technology","ror":"https://ror.org/00ys1hz88","country_code":"JP","type":"education","lineage":["https://openalex.org/I85922643"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Masahiro Iwahashi","raw_affiliation_strings":["Nagaoka University of Technology, Japan"],"affiliations":[{"raw_affiliation_string":"Nagaoka University of Technology, Japan","institution_ids":["https://openalex.org/I119806805","https://openalex.org/I85922643"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5070872826","display_name":"Eng Siong Chng","orcid":"https://orcid.org/0000-0001-6257-7399"},"institutions":[{"id":"https://openalex.org/I172675005","display_name":"Nanyang Technological University","ror":"https://ror.org/02e7b5302","country_code":"SG","type":"education","lineage":["https://openalex.org/I172675005"]}],"countries":["SG"],"is_corresponding":false,"raw_author_name":"Eng Siong Chng","raw_affiliation_strings":["Temasek Laboratories, Nanyang Technological University (NTU), Singapore"],"affiliations":[{"raw_affiliation_string":"Temasek Laboratories, Nanyang Technological University (NTU), Singapore","institution_ids":["https://openalex.org/I172675005"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5032690182","display_name":"Haizhou Li","orcid":"https://orcid.org/0000-0001-9158-9401"},"institutions":[{"id":"https://openalex.org/I165932596","display_name":"National University of Singapore","ror":"https://ror.org/01tgyzw49","country_code":"SG","type":"education","lineage":["https://openalex.org/I165932596"]}],"countries":["SG"],"is_corresponding":false,"raw_author_name":"Haizhou Li","raw_affiliation_strings":["Department of Electrical and Computer Engineering, National University of Singapore","School of Computer Science and Engineering, NTU, Singapore"],"affiliations":[{"raw_affiliation_string":"Department of Electrical and Computer Engineering, National University of Singapore","institution_ids":["https://openalex.org/I165932596"]},{"raw_affiliation_string":"School of Computer Science and Engineering, NTU, Singapore","institution_ids":[]}]}],"institutions":[],"countries_distinct_count":3,"institutions_distinct_count":7,"corresponding_author_ids":["https://openalex.org/A5083198820"],"corresponding_institution_ids":["https://openalex.org/I119806805","https://openalex.org/I85922643"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.22156723,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":"18","issue":null,"first_page":"1","last_page":"5"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10860","display_name":"Speech and Audio Processing","score":1.0,"subfield":{"id":"https://openalex.org/subfields/1711","display_name":"Signal Processing"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},"topics":[{"id":"https://openalex.org/T10860","display_name":"Speech and Audio Processing","score":1.0,"subfield":{"id":"https://openalex.org/subfields/1711","display_name":"Signal Processing"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},{"id":"https://openalex.org/T10201","display_name":"Speech Recognition and Synthesis","score":0.9994999766349792,"subfield":{"id":"https://openalex.org/subfields/1702","display_name":"Artificial Intelligence"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},{"id":"https://openalex.org/T11309","display_name":"Music and Audio Processing","score":0.9968000054359436,"subfield":{"id":"https://openalex.org/subfields/1711","display_name":"Signal Processing"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.7197147607803345},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6543759703636169},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.5887644290924072},{"id":"https://openalex.org/keywords/channel","display_name":"Channel (broadcasting)","score":0.5676983594894409},{"id":"https://openalex.org/keywords/filter-bank","display_name":"Filter bank","score":0.5553558468818665},{"id":"https://openalex.org/keywords/feature","display_name":"Feature (linguistics)","score":0.5182604789733887},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.4746423661708832},{"id":"https://openalex.org/keywords/beamforming","display_name":"Beamforming","score":0.4367799162864685},{"id":"https://openalex.org/keywords/feature-vector","display_name":"Feature vector","score":0.4342394173145294},{"id":"https://openalex.org/keywords/microphone-array","display_name":"Microphone array","score":0.4264594614505768},{"id":"https://openalex.org/keywords/diagonal","display_name":"Diagonal","score":0.42402926087379456},{"id":"https://openalex.org/keywords/microphone","display_name":"Microphone","score":0.3839561939239502},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.22875192761421204},{"id":"https://openalex.org/keywords/telecommunications","display_name":"Telecommunications","score":0.07714986801147461}],"concepts":[{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.7197147607803345},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6543759703636169},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.5887644290924072},{"id":"https://openalex.org/C127162648","wikidata":"https://www.wikidata.org/wiki/Q16858953","display_name":"Channel (broadcasting)","level":2,"score":0.5676983594894409},{"id":"https://openalex.org/C100515483","wikidata":"https://www.wikidata.org/wiki/Q3268235","display_name":"Filter bank","level":3,"score":0.5553558468818665},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.5182604789733887},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4746423661708832},{"id":"https://openalex.org/C54197355","wikidata":"https://www.wikidata.org/wiki/Q5782992","display_name":"Beamforming","level":2,"score":0.4367799162864685},{"id":"https://openalex.org/C83665646","wikidata":"https://www.wikidata.org/wiki/Q42139305","display_name":"Feature vector","level":2,"score":0.4342394173145294},{"id":"https://openalex.org/C2778806681","wikidata":"https://www.wikidata.org/wiki/Q907293","display_name":"Microphone array","level":4,"score":0.4264594614505768},{"id":"https://openalex.org/C130367717","wikidata":"https://www.wikidata.org/wiki/Q189791","display_name":"Diagonal","level":2,"score":0.42402926087379456},{"id":"https://openalex.org/C2778263558","wikidata":"https://www.wikidata.org/wiki/Q46384","display_name":"Microphone","level":3,"score":0.3839561939239502},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.22875192761421204},{"id":"https://openalex.org/C76155785","wikidata":"https://www.wikidata.org/wiki/Q418","display_name":"Telecommunications","level":1,"score":0.07714986801147461},{"id":"https://openalex.org/C68115822","wikidata":"https://www.wikidata.org/wiki/Q1068172","display_name":"Sound pressure","level":2,"score":0.0},{"id":"https://openalex.org/C2524010","wikidata":"https://www.wikidata.org/wiki/Q8087","display_name":"Geometry","level":1,"score":0.0},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.0},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/iscslp.2016.7918435","is_oa":false,"landing_page_url":"https://doi.org/10.1109/iscslp.2016.7918435","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2016 10th International Symposium on Chinese Spoken Language Processing (ISCSLP)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/16","score":0.5600000023841858,"display_name":"Peace, Justice and strong institutions"}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":18,"referenced_works":["https://openalex.org/W1509052650","https://openalex.org/W1514905536","https://openalex.org/W1592062602","https://openalex.org/W1973669708","https://openalex.org/W1992475611","https://openalex.org/W1998229164","https://openalex.org/W2000359198","https://openalex.org/W2002342963","https://openalex.org/W2060108923","https://openalex.org/W2099984896","https://openalex.org/W2129227482","https://openalex.org/W2130361043","https://openalex.org/W2139065479","https://openalex.org/W2289394825","https://openalex.org/W2343348669","https://openalex.org/W4206633762","https://openalex.org/W4295679937","https://openalex.org/W6610836755"],"related_works":["https://openalex.org/W2896203542","https://openalex.org/W876328409","https://openalex.org/W4319068615","https://openalex.org/W4214946933","https://openalex.org/W1879255185","https://openalex.org/W2148473678","https://openalex.org/W2769861442","https://openalex.org/W3004719695","https://openalex.org/W2120442551","https://openalex.org/W1980506188"],"abstract_inverted_index":{"In":[0],"this":[1],"paper,":[2],"we":[3],"propose":[4],"a":[5,62,139],"feature":[6,103,119],"adaptation":[7,104,120],"method":[8,25,121],"that":[9,116],"combines":[10],"speech":[11,20],"features":[12,29,60],"from":[13,68,131],"multiple":[14],"microphone":[15],"channels":[16,32,41],"for":[17,45,76],"robust":[18],"automatic":[19],"recognition":[21],"(ASR).":[22],"The":[23,48],"proposed":[24,102,118],"first":[26],"transforms":[27,125],"the":[28,40,55,58,80,86,90,94,101,106,111,117,152,156],"in":[30,85,93,110],"all":[31],"using":[33],"channel-dependent":[34,124],"linear":[35],"transforms,":[36],"and":[37],"then":[38],"sum":[39],"into":[42],"one":[43],"channel":[44],"acoustic":[46,141],"modeling.":[47],"transform":[49],"parameters":[50],"are":[51],"estimated":[52],"by":[53,155],"maximizing":[54],"likelihood":[56,81],"of":[57],"transformed":[59],"on":[61,105],"Gaussian":[63],"mixture":[64],"model":[65,142],"(GMM)":[66],"trained":[67],"clean":[69],"features.":[70],"To":[71],"use":[72],"diagonal":[73,123],"covariance":[74],"matrices":[75],"efficient":[77],"estimation":[78],"algorithm,":[79],"function":[82],"is":[83,92,143,147],"evaluated":[84],"cepstral":[87],"domain,":[88],"while":[89],"transformation":[91],"log":[95],"Mel":[96],"filterbank":[97],"domain.":[98],"We":[99],"evaluate":[100],"6-channel":[107],"evaluation":[108],"data":[109],"CHiME-3":[112],"task.":[113],"Results":[114],"show":[115],"with":[122],"reduces":[126],"word":[127],"error":[128],"rate":[129],"(WER)":[130],"21.05%":[132],"(best":[133],"single":[134],"channel)":[135],"to":[136],"16.96%":[137],"when":[138],"DNN-based":[140],"used.":[144],"This":[145],"result":[146],"also":[148],"slightly":[149],"better":[150],"than":[151],"17.60%":[153],"obtained":[154],"minimum":[157],"variance":[158],"distortionless":[159],"response":[160],"beamforming.":[161]},"counts_by_year":[],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}